High-resolution CT (HRCT) is currently the primary method for polymyositis/dermatomyositis-related interstitial lung disease (PM/DM-ILD). Its imaging features highly consistent with the pathological classification of interstitial lung disease and are crucial for monitoring disease progression. The HRCT imaging characteristics, combined with myositis-specific antibodies and the occurrence of spontaneous pneumomediastinum, provide valuable insights for predicting disease progression and prognosis. Additionally, artificial intelligence plays a significant role in rapidly identifying PM/DM-ILD patients with poor prognosis. This article reviews HRCT manifestations and explores the application value of HRCT in assessing disease progression and prognosis of PM/DM-ILD patients.

In 2024, the American Heart Association (AHA) issued a scientific statement on the diagnosis and management of cardiac sarcoidosis (CS), systematically outlining the diagnostic and therapeutic framework for this infiltrative cardiomyopathy characterized by non-necrotizing granulomatous inflammation. The Statement emphasizes that multimodal imaging is a core pillar of CS diagnosis. This article focuses on the core content of the statement, specifically interpreting the clinical application value and diagnostic standards of multimodal imaging techniques for CS, as well as the collaborative diagnostic and therapeutic strategies involving cardiac magnetic resonance (CMR) and positron emission tomography (PET), with the aim of providing precise imaging assessment pathways for clinical practice.

Photon-counting CT (PCD-CT), compared to conventional CT, offers higher spatial resolution, lower radiation dose, reduced use of iodine contrast agents, and superior image quality, and it has gradually been introduced into clinical practice. PCD-CT demonstrates advantages across various body systems, particularly in the detailed imaging of coronary artery stenosis, plaque composition, and stents. By reviewing foreign literature and current domestic exploration of PCD-CT applications, the prospects for its clinical research and application in China are discussed.

Ultrafast dynamic contrast-enhanced (UF-DCE) MRI, with its advantages of high imaging speed, high temporal resolution, and the ability to obtain rich hemodynamic parameters, has been utilized in the early screening, differential diagnosis, neoadjuvant chemotherapy efficacy prediction, and prognostic evaluation of breast cancer. This review summarizes the technical principles of UF-DCE MRI, its applications in breast cancer diagnosis and treatment, and the research progress on artificial intelligence applications in UF-DCE MRI.

Objective To explore the differences in MRI features among different clinical subtypes of children with juvenile idiopathic arthritis (JIA) and to analyze the correlation between MRI features and clinical scores. Methods MRI images and clinical data from 55 children with JIA, aged 1-14 years (mean age 8.1±4.1 years), were retrospectively collected. The children were divided into four clinical subtypes: systemic (12 cases), polyarthritic (17 cases), oligoarthritic(16 cases), and enthesities-related arthritis(ERA) (10 cases). MRI features, such as synovial hyperplasia and bone marrow edema in both large and small joints, were observed, and bone marrow edema and synovial hyperplasia were scored. One-way ANOVA, Welch test or Chi-square test were used to compare clinical data and imaging features among the four groups. Pearson test or Spearman test was used to evaluate the correlation between imaging features and clinical scores. Results Among the 55 children, 35 had synovial hyperplasia and 33 had bone marrow edema. There were significant differences in erythrocyte sedimentation rate (ESR), HLA-B27, and foot/ankle involvement among the four subtypes (P<0.05). The oligoarthritic subtype had a significantly higher proportion of foot/ankle involvement compared to the systemic and ERA subtypes (all P<0.05), while other clinical subtypes did not show specific joint involvement. The incidence of synovial hyperplasia was higher in polyarthritic and oligoarthritic patients, while bone marrow edema was more common in the ERA patients. The systemic patients mostly showed only joint effusion (all P<0.05). Comparison of joint scores among the four subtypes revealed that ERA patients had higher bone marrow edema scores in large joints, while polyarthritic and oligoarthritic patients had higher scores for small joints (all P<0.05). However, there was no significant difference in synovial hyperplasia scores (all P>0.05). In large joint, the scores of bone marrow edema were positively correlated with ESR, C-reaction protein(CRP), and age, and the scores of synovial hyperplasia were positively correlated with age and symptom duration (all P<0.05). In small joints, bone marrow edema scores were positively correlated with ESR and CRP (all P<0.05). Conclusion The affected joints and MRI features in JIA patients vary between clinical subtypes, and the severity of joint lesions is highly correlated with clinical indexes.

Amyloid-related imaging abnormalities (ARIA) are among the most common adverse reactions during Aβ monoclonal antibody treatment for early Alzheimer’s disease (AD). Magnetic resonance imaging (MRI) serves as a crucial tool tool for monitoring the occurrence of ARIA and assessing its severity throughout the treatment process. This paper provides a detailed overview of the mechanisms of ARIA, its imaging manifestations, and severity grading. Additionally, a comprehensive standard MRI examination protocol and monitoring workflow are proposed based on clinical practice experience. The study also highlights the critical role of imaging monitoring in guiding clinical medication for AD patients.

Squamous cell carcinoma is the most common malignancy of the head and neck. Dual-energy CT (DECT) can be used to observe the morphological characteristics of head and neck squamous cell carcinoma (HNSCC) and further evaluate the functional changes of affected tissues through virtual monoenergetic images, virtual non-contrast images, iodine maps, and other post-processed images. Currently, the application of DECT in HNSCC is primarily focused on laryngeal and hypopharyngeal squamous cell carcinoma. This paper reviews the research progress of DECT in the diagnosis and differential diagnosis, staging, pathological grading, prognosis prediction, efficacy evaluation, and recurrence diagnosis of HNSCC.

Objective To summarize the imaging features of axial bone lesions in ankylosing spondylitis(AS), analyze the injury characteristics and imaging manifestations of spinal fractures in patients with AS, and improve the understanding of the disease. Methods A retrospective analysis was conducted on the X-ray, CT, and MRI imaging data of 88 clinically diagnosed AS patients. Sacroiliac joint lesions, spinal lesions, and associated spinal fractures were observed, and the affected locations and number of lesions were recorded. The detection rates of different grades of sacroiliac joint lesions were compared between X-ray and CT imaging, and the detection rates of bone erosion, sclerosis, and joint space changes between CT and MRI were calculated. The χ² test was used to compare differences in detection rates. Results Of the 88 patients, 87 (98.86%) had sacroiliac joint involvement. X-ray and CT images showed bilateral sacroiliac joint surface roughness, erosive destruction, marginal sclerosis, joint space widening or narrowing, and partial fusion or complete bony ankylosis of the sacroiliac joints. MRI of the sacroiliac joint was performed on 27 patients, and most showed bone erosion, bone marrow edema, fat deposition, and sclerosis. A few cases exhibited synovitis of the joint space, sacroiliac bursitis, enthesitis, or sacroiliac joint ankylosis with disappearance of the joint space. X-ray detection rates for grade Ⅰ lesions were higher than CT, but lower for grade Ⅱlesions (both P<0.05). CT had a higher detection rate for subchondral sclerosis compared to MRI (P<0.05). Sixty-five patients (73.86%) had spinal involvement, including 38 cases of spinal ankylosis. Twenty-four patients had spondylitis at vertebral corners (Romanus lesions), predominantly in the thoracolumbar and lumbar regions. Fifteen patients had intervertebral discitis (Andersson lesions), mainly affecting the mid-lower thoracic and lumbar vertebrae. Spinal fractures were observed in 24 patients (27.27%), 14 had acute fractures, most commonly in the lower cervical spine (C5-7, 8 cases), while 10 had old fractures, all located in the thoracolumbar spine (most frequently T11-12, 3 cases). Conclusion The imaging manifestations of axial bone lesions in AS have certain characteristics. Spinal fractures in AS patients often involve the three columns of the spine and are prone to spinal cord injury and pseudarthrosis, which requires special attention.

Magnetic resonance imaging (MRI), as a tool for evaluating multi-organ impairment due to liver cirrhosis, enables precise identification of microstructural abnormalities and effective evaluation of organ function. When combined with clinical and laboratory indicators, MRI facilitates monitoring of disease progression and treatment efficacy, supporting the development of diagnostic and therapeutic strategies. This article reviews the current applications of MRI in diagnosing and managing multi-organ damage resulting from liver cirrhosis, highlighting advancements and value of both conventional and functional MRI in monitoring disease, evaluating treatment effectiveness, and predicting long-term outcomes for hepatic encephalopathy, cirrhosis-related injury, and hepatocardiac syndrome. Finally, it discusses future directions for development.

Objective To investigate the value of the 2018 Liver Image Reporting and Data System (LI-RADS v2018) and other imaging features based on preoperative Gd-EOB-DTPA-enhanced MRI in predicting vascular encapsulating tumor clusters (VETC) and microvascular invasion (MVI) in hepatocellular carcinoma (HCC), constructing a predictive model and assessing its risk stratification capability. Methods This study retrospectively included 232 HCC patients who underwent curative liver resection. Based on the VETC and MVI status, patients were categorized into the VETC and MVI positive HCC group [VM (+) group] (46 patients) and the VETC or MVI negative HCC group [non-VM (+) group] (186 patients). Multivariate logistic regression analysis was used to identify the independent predictors of VM (+) HCC and to construct a combined model. The predictive efficacy of single predictors and the combined model was assessed using receiver operating characteristic (ROC) curves, and the area under the curve (AUC), sensitivity, and specificity were calculated. The predictor or model with the highest AUC was selected for survival analysis, and a statistical cutoff value for predictive probability was set based on the maximum Yoden index of the ROC curve to categorize HCC patients into high and low risk groups. Kaplan-Meier survival curves were used to evaluate recurrence-free survival (RFS) and early recurrence (ER) between the high-risk and low-risk groups, as well as between VM(+) and non-VM(+) HCC patients. Results Multivariate logistic regression analysis revealed that tumor size, peritumoral enhancement during the arterial phase, and peritumoral hypointensity during the hepatobilary phase were independent predictors of VM(+) HCC. The combined model incorporating these three factors achieved an AUC of 0.792, with sensitivity of 80.4% and specificity of 74.2%. DeLong's test showed that the AUC of the combined model for predicting VM (+) HCC was higher than that of any single predictor (all P<0.05). Kaplan-Meier survival analysis demonstrated the RFS was shorter and the ER risk was higher in the VM(+) group compared to the non-VM(+) group, and similarly,the high-risk group predicted by the combined model had shorter RFS and higher ER risk than the low-risk group (P<0.05). Conclusion The combined model based on tumor size, peritumoral enhancement during the arterial phase, and peritumoral hypointensity during the hepatobilary phase can be used for preoperative prediction of VM(+) HCC. The coexistence of VETC and MVI is associated with an increased risk of ER and decreased RFS following HCC resection.

Dual energy CT (DECT) produces multiple energy spectrum image sets by using X-ray with two different energy levels. Compared to conventional CT, DECT virtual monoenergetic images (VMI) can enhance contrast between vessels and surrounding structures, improve lesion detection, reduce artifacts, and minimize radiation exposure in CT angiography (CTA). The VMI technique improves the quality of CTA, thereby reducing the failure rate of the examination. Furthermore, the VMI technique allows for better evaluation of plaque components, thrombi, vascular details, and small vessel branches. The advantages of VMI are highly significant for procedures involving blood vessels, including surgical and interventional therapies for vascular diseases. This article reviews the research progress and clinical applications of VMI in vascular imaging.

Breast cancer is the most common malignancy in women, with diverse subtypes and treatment options, making early diagnosis and classification critical. Dual-energy CT (DECT) enhances material differentiation by utilizing two distinct X-ray energy levels. The iodine density maps generated through post-processing provide clear visualization of breast cancer lesions and the extent of internal duct expansion. Additionally, DECT yields multiple parameters that aid in molecular typing, as well as in predicting metastasis, prognosis, and treatment efficacy for breast cancer. This article reviews the application and research progress of DECT in breast cancer.

Triple-negative breast cancer (TNBC) is highly heterogeneous, and precise preoperative diagnosis is crucial for patient treatment and prognosis. Radiomics, which enables the high-throughput extraction of tumor microfeatures, holds high significant potential in distinguishing between benign and malignant breast lesions, breast cancer types, grading, and in predicting treatment responses and recurrence risks, especially applied in the field of non-invasive prediction of molecular types and the evaluation of tumor heterogeneity. This paper reviews the research progress of radiomics based on mammography, ultrasonography, and MRI in predicting TNBC.

Radiomics is a technique that extracts quantitative information from medical images for characterization and analysis, providing supplementary information for the diagnosis and treatment of clinical diseases. Feature selection plays a crucial role in radiomics by enhancing the accuracy and predictive performance of machine learning models. This paper reviews the classification, advantages, and disadvantages of feature selection methods in radiomics, their applications, and factors that influence the accuracy and stability of feature selection.

Objective This study aims to evaluate the feasibility of low-dose chest CT (LD-CT) using photon-counting detector CT (PCD-CT) for the detection, quantification, and risk stratification of coronary artery calcium. Methods A retrospective analysis was conducted on 63 patients with coronary artery calcium who underwent standard calcium scoring CT (ECG-CT) and LD-CT with PCD-CT, a total of 189 vessels involved. Twenty-nine patients were divided into high heart rate group (heart rate >75 beats/min) and 34 patients into low heart rate group (heart rate <75 beats/min). ECG-CT was performed using a prospective ECG-gated 120 kVp scan, while LD-CT utilized non-ECG-gated high-pitch combined with tin filtration at 100 kVp (Sn100 kVp) settings. The Agatston score was used for quantifying coronary artery calcium. Using ECG-CT as the reference standard, the sensitivity, specificity, and accuracy of LD-CT in detecting coronary artery calcification were calculated at both patient and vessel levels, as well as at high and low heart rates. The correlation and agreement between LD-CT and ECG-CT in assessing AS were analyzed by the Spearman correlation coefficient (r) and Bland-Altman method (bias: 95% limits of agreement). The agreement of coronary artery calcification risk stratification was assessed by the Weighted Kappa analysis. The difference in effective radiation doses between LD-CT and ECG-CT was compared using the paired t-test. Results ECG-CT detected coronary artery calcification in 130 vessels across all 63 patients. For all patients, LD-CT showed high accuracy(100%) in detecting coronary artery calcification. A strong correlation (r=0.95~0.99，P<0.05) and consistency (-9.7：-125/105.7) were observed between the Agatston scores obtained from both methods. The bias in the left anterior descending artery (LAD) (0.1：-102.8/102.9) was smaller than the left circumflex artery (LCX) (-11.5：-86.9/63.9) and the right coronary artery(RCA) (-8.1:-81.2/65.1). The bias in the low heart rate group (-3.3： -73.4/66.5) was smaller than in the high heart rate group(-18.3：-175.3/138.6). Strong agreement was found in risk stratification based on Agatston scores (kappa=0.963). The effective radiation dose of LD-CT (0.48±0.9 mSv) was 37% (P<0.001) lower than that of ECG-CT (0.77±0.16 mSv). Conclusion LD-CT using PCD-CT not only demonstrated better accuracy in the detection, quantification, and risk stratification of coronary artery calcium but also significantly reduced effective radiation dose.

Objective To explore the classification of Andersson lesions in ankylosing spondylitis (AS) using MRI and analyze the vertebral units involved in different classifications, providing imaging evidence for the early diagnosis and treatment of AS. Methods All of 77 patients with ankylosing spondylitis who underwent whole spinal MRI were retrospectively included, with 69 males and 8 females, and an average age of 44.0±12.2 years. General clinical data and whole-spine MRI images of the patients were collected. Two physicians analyzed the MRI characteristics of Andersson lesions and the involved vertebral units. According to Kim's classification, the lesions were classified into types Ⅰ-Ⅴ. The Kappa test was used to analyze the consistency between the two physicians in classifying Andersson lesions. Results The consistency between the two physicians in diagnosing and classifying Andersson lesions was good (κ=0.694, P<0.001). A total of 229 vertebral units were involved in Andersson lesions, with 208 vertebral units showing only one type of lesion. Types Ⅰ-Ⅴ Andersson lesions involved 30 (13.1%), 57 (24.9%), 13 (5.7%), 85 (37.1%), and 23 (10.0%) vertebral units, respectively. Twenty-one vertebral units had two types of lesions simultaneously, with 18 units being type Ⅰ+Ⅱ, 1 unit type Ⅱ+Ⅲ, and 2 units type Ⅰ+Ⅲ. Conclusion MRI can clearly display Andersson lesions in ankylosing spondylitis and can be used to classify them, which is of great value for the early diagnosis and treatment plans for AS.

Habitat imaging(HI) can analyze tumor heterogeneity and microenvironmental characteristics and has been increasingly applied in the research, diagnosis, and treatment of common digestive system tumors, including colorectal cancer, gastric cancer, and hepatocellular carcinoma. Currently, HI is used to construct genotypic prediction models, precision staging, and metastasis prediction in colorectal cancer; to quantify immune microenvironment characteristics, evaluate treatment response, and predict prognosis in gastric cancer; and to achieve non-invasive identification of microvascular invasion and recurrence risk stratification in hepatocellular carcinoma. This article introduces the basic principles and technical processes of HI, and reviews its research progress in the above-mentioned digestive system tumors.

Objective To explore the value of a machine learning model incorporating primary tumor and peritumoral radiomics features for preoperative prediction of lymphovascular invasion (LVI) in gastric cancer. Methods Clinical and imaging data of 148 patients with pathologically confirmed gastric cancer were retrospectively collected. Based on pathological results, patients were divided into an LVI-positive group (79 cases) and an LVI-negative group (69 cases). Patients were randomly divided into a training set (103 cases) and a test set (45 cases) in a 7∶3 ratio. Radiomic features were extracted from the primary tumor and peritumoral regions. The least absolute shrinkage and selection operator (LASSO) method was used to select optimal radiomic features, and the radiomics score (Rad-score) was calculated. The clinical features with statistically significant differences between the two groups were combined with Rad-score for multivariate logistic regression analysis to select variables for constructing a machine learning model. Seven machine learning algorithms, including logistic regression (LR), extreme gradient boosting (XGBoost), random forest (RF), Gaussian naive Bayes (GNB), support vector machine (SVM), light gradient boosting machine (LightGBM), and K-nearest neighbors (KNN), were used to construct clinical-radiomics models. The performance of the models was evaluated using receiver operating characteristic (ROC) curve analysis. Calibration curves and decision curve analysis (DCA) were used to assess the calibration degree and clinical net benefit of the models, respectively. The SHapley Additive exPlanations (SHAP) method was employed to provide visual interpretation of the predictive model. Results In the training set, all seven machine learning models achieved an AUC greater than 0.650, with the RF model achieving the highest AUC (0.858), sensitivity (0.895), and accuracy (0.776). The calibration curve indicated that the RF model had the lowest Brier score (0.153), demonstrating the best predictive accuracy. DCA revealed that the RF model provided the highest net clinical benefit when the risk threshold ranged from 0.30 to 0.70. In the test set, the RF model maintained stable diagnostic performance, achieving an AUC of 0.821. SHAP analysis identified key factors associated with LVI risk in gastric cancer patients and provided visual interpretation for individual predictions. Conclusion The RF model, integrating primary tumor and peritumoral radiomic features with clinical factors, holds significant value for preoperative prediction of LVI status in gastric cancer patients.

Objective To compare the diagnostic performance of a gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI hepatobiliary phase radiomics model and ultrasound elastography (UE) in assessing non-significant liver fibrosis. Additionally, to investigate whether combining radiomics features with other parameters into a joint model can improve diagnostic efficiency. Methods This retrospective study included 201 patients with chronic liver disease from two hospitals who underwent both Gd-EOB-DTPA-enhanced MRI and UE. Patients were classified into non-significant and significant groups based on pathological results. The dataset was divided into a training set of 152 cases (38 non-significants, 114 significants) and a test set of 49 cases (11 non-significants, 38 significants) according to hospital origin. Clinical indicators with significant differences between the two groups were selected for logistic regression analysis to establish a clinical model. Liver stiffness measurement (LSM) values were obtained from UE. Radiomics features were extracted from hepatobiliary phase MRI images, and a radiomics model was developed using the least absolute shrinkage and selection operator (LASSO) regression algorithm with 10-fold cross-validation. A clinical-ultrasound combined model and a clinical-ultrasound-radiomics combined nomogram model were constructed. The performance of multiple models and parameter were sequentially analyzed using receiver operating characteristic (ROC) curves, and the performance differences were compared by DeLong test. Calibration curves were used to assess the consistency between predicted outcomes and actual pathological gradings. Decision curve analysis (DCA) was used to evaluate the clinical value of each model. Results In both the training and test sets, the diagnostic performance of the radiomics model, LSM, and clinical model for non-significant liver fibrosis was similar, with no statistically significant differences (all P>0.05). The diagnostic performance of the clinical-ultrasound combined model was higher than the clinical model and LSM (all P<0.05); the diagnostic performance of the clinical-ultrasound-radiomics combined nomogram model for diagnosing non-significant liver fibrosis was superior to the other models and LSM (all P<0.05). Calibration curves assessment showed good consistency between the predictions of the clinical-ultrasound-radiomics combined nomogram model and actual results, while DCA demonstrated that the nomogram model had the highest net benefit across a threshold probability range of 10% to 92%. Conclusion The diagnostic performance of the Gd-EOB-DTPA-enhanced MRI hepatobiliary phase radiomics model is comparable to the LSM from UE for non-significant liver fibrosis. However, combining multiple parameters into a joint model significantly improves diagnostic accuracy.

Objective To construct a machine learning model based on multimodal radiomic features and explore its ability to noninvasively predict the mutation status of alpha thalassemia/mental retardation syndrome X-linked (ATRX) gene in isocitrate dehydrogenase (IDH) mutant lower-grade gliomas (LrGG) preoperatively. Methods A retrospective analysis was conducted on the imaging and clinical data of 102 patients pathologically and molecularly confirmed as IDH-mutant LrGG. Of these, 47 cases had ATRX mutations, and 55 cases were wild-type. Patients were randomly divided into a training set (71 cases) and a test set (31 cases) in a 7∶3 ratio. A total of 3 318 radiomic features were extracted from contrast-enhanced (CE)-T₁WI, apparent diffusion coefficient (ADC) maps, and ¹⁸F-FDG PET images. The radiomic features were categorized into five datasets based on the imaging source: CE-T₁WI dataset, ADC dataset, PET dataset (¹⁸F-FDG PET), MRI dataset (CE-T₁WI+ADC), and combined dataset (CE-T₁WI+ADC+¹⁸F-FDG PET). Four feature dimensionality reduction methods [linear discriminant analysis (LDA), principal component analysis (PCA), Wilcoxon-based correlation selection, and least absolute shrinkage and selection operator (LASSO)] and four machine learning algorithms [support vector machine (SVM), logistic regression (LR), K-nearest neighbors (KNN), random forest (RF)] were combined to construct 16 predictive models based on the combined dataset, and their performance was evaluated to determine the optimal algorithm combination. The optimal algorithm was then applied to the CE-T₁WI, ADC, PET, MRI, and combined datasets to build models. Receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC) was calculated to assess the predictive performance of each model. Results Among the 16 predictive models constructed based on the combined radiomic features, the model combining LASSO with RF had the best predictive performance, with AUCs of 0.967 and 0.950 in the training and test sets, respectively. Among the four feature reduction methods, models using LASSO showed the best overall performance; among the four machine learning algorithms, RF yielded the highest predictive performance. When applied to the CE-T₁WI, ADC, PET, MRI, and combined datasets, the model demonstrated the best predictive performance in the combined dataset, with AUCs of 0.967 and 0.950 in the training test and test sets, respectively, followed by the MRI and PET datasets (AUCs of 0.931 and 0.915, respectively). Conclusion The machine learning model combining LASSO and RF algorithms based on multimodal radiomic features has high efficiency in predicting ATRX mutation status in IDH-mutant LrGG. This method is non-invasive and straight forward.

Objective Investigating the CT and MRI characteristics of intrahepatic biliary adenofibroma (BAF) to improve the understanding of this tumor. Methods We conducted a retrospective analysis of the CT and MRI findings from one case confirmed by pathology as BAF, alongside a review of relevant literature. Results The CT plain scan reveals a slightly hypodense mass in the right liver lobe, with poorly defined borders, and punctate calcifications within. On contrast-enhanced scans, the margins and internal septa of the lesion exhibited progressive marked enhancement, with some exhibiting vascular-like enhancement, while the cystic components show no enhancement. MRI demonstrated an abnormal signal mass in the right liver lobe, with unclear borders, multiple septa, and a honeycomb-like appearance. On T₁-weighted imaging (T₁WI), the mass showed slightly low to low signal intensity, while on T₂-weighted imaging (T₂WI), it displayed slightly high to high signal intensity. Diffusion-weighted imaging (DWI) indicated slightly high signal intensity, and the apparent diffusion coefficient (ADC) values were increased. On enhanced scans, the lesion’s margins and septa showed progressive enhancement, with localized high signals during the hepatic-biliary phase. Conclusion BAF is a rare entity with distinctive imaging features that may aid in differentiating between benign and malignant lesions. A definitive diagnosis, however, requires pathological and immunohistochemical examination.

Radiology plays a pivotal role in the diagnosis and treatment of traumatic brain injury (TBI), enabling the identification of brain injury types and assessment of injury severity. In clinical practice, CT and MRI are routinely used for diagnosing and evaluating TBI. In recent years, artificial intelligence (AI) has gradually been integrated into imaging for the clinical management of TBI, including the identification cranial anatomical structures, extraction of imaging features, segmentation and quantification of injury areas, prognosis assessment, and decision-making support. This article reviews the progress of AI algorithms and their clinical applications in TBI patients.

Objective To establish a logistic regression model based on CT and MRI features of multilocular hepatic cysts and mucinous cystic tumors (MCN), and analyze its value in differential diagnosis between the two entities. Methods A retrospective analysis was conducted on CT and MRI data from 65 cases of multilocular hepatic cystic lesions, including 13 males and 52 females. According to surgical pathology results, the cases were divided into hepatic cyst lesions (39 cases) and hepatic MCN lesions (26 cases). Chi-square tests were used to compare imaging findings between the two groups. Statistically significant CT and MRI features were further analyzed using multivariate logistic regression to construct a binary logistic regression model. The predictive performance of the model was evaluated using the receiver operating characteristic (ROC) curve, and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated. Results Significant differences were observed between hepatic cysts and hepatic MCNs in terms of the number of hepatic cystic lesions, the appearance of cyst wall and septa, nodular protrusions of cyst wall or septa, the thickness of solid components greater than 10 mm, types of septa, septa location, and the relationship between septa and cyst walls between hepatic cysts and hepatic MCNs (all P<0.05). Multivariate logistic regression analysis identified that septal type, and the relationship between septa and cyst walls as independent predictive factors (P<0.05). A logistic regression model constructed using these two factors achieved higher diagnostic performance (AUC=0.871) compared to using septal type (AUC=0.699) or the relationship between septa and cyst walls (AUC=0.795) alone. Conclusion A logistic regression model incorporating septal type, and the relationship between septa and cyst walls can effectively distinguish multilocular hepatic cysts from hepatic MCN, improving the preoperative imaging diagnostic accuracy for these lesions.

Rheumatology imaging techniques can accurately identify inflammatory and structural changes in joints.Combined with clinical and laboratory tests, these techniques can monitor treatment efficacy, predict disease progression, and guide clinical treatment plans. Focusing on the use of rheumatology imaging in clinical diagnosis and treatment of rheumatic diseases, as well as in the disease progression process, this paper explores the advancements and value of various imaging techniques such as whole-body MRI, quantitative MRI, low-dose CT, dual-energy CT, synthesized CT, and machine-learning methods in early diagnosis, differential diagnosis, treatment monitoring, and prognosis prediction of rheumatic diseases, thereby clarifying the future direction of rheumatology imaging development.

Objective To explore the diagnostic performance of a spectral CT-based radiomics machine learning model and nomogram for preoperatively identifying the KRAS gene status in patients with colorectal cancer (CRC). Methods A total of 137 CRC patients who underwent KRAS mutation detection and preoperative spectral CT examination were retrospectively included (70 cases with KRAS wild type and 67 cases with KRAS mutant type). They were randomly divided into a training set (95 cases) and a test set (42 cases) in a 7∶3 ratio. Tumor region of interest (ROI) was delineated on venous-phase 70 keV monochromatic enhanced CT images, and radiomics features were extracted and selected. A radiomics score (Rad-score) was calculated using least absolute shrinkage and selection operator (LASSO) regression. Six models were established including three radiomics models based on support vector machine (SVM), extreme gradient boosting (XGBoost), and logistic regression (LR), as well as three combined models integrating spectral CT imaging features with the Rad-score. Model performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), and compared using the Delong test. A radiomics nomogram was constructed based on the Rad-score and validated in the test set. Calibration curves, decision curve analysis (DCA), and clinical impact curves were used to assess calibration, clinical net benefit, and clinical utility. Results A total of 8 radiomics features and 1 spectral parameter were selected. In the test set, the LR-based combined model demonstrated the best performance, with an AUC of 0.891, outperforming the combined models based on SVM (AUC=0.796), XGBoost (AUC=0.787), and LR (AUC=0.812) (all P<0.05), as well as the combined models based on SVM (AUC=0.889) and XGBoost (AUC=0.873) (both P<0.05). The nomogram model achieved AUCs of 0.987 and 0.916 in the training and test sets, respectively. The calibration curve showed good agreement in the training set, while performance in the test set was slightly lower. DCA and clinical impact curves demonstrated that the nomogram provided favorable clinical net benefit and utility. Conclusion The LR-based model and nomogram, constructed using venous-phase spectral CT and radiomics features, offer valuable preoperative insights into KRAS gene status in CRC patients and may serve as a reference for clinical decision-making.

Objective To explore the imaging characteristics of primary cervical NK/T-cell lymphoma (NKTCL) with secondary peripheral nerve lymphomatosis, improving understanding of the disease and providing a reference for diagnosis and treatment decision. Methods A retrospective analysis was conducted on the clinical data, CT, MRI, and ¹⁸F-FDG PET/CT imaging findings of a patient with primary cervical NKTCL over a 9-month treatment period. Relevant literatures were also reviewed. Results The patient was admitted to hospital with vaginal fluid as the first symptom. Pre-treatment CT examination showed that the cervix was significantly enlarged, showing an irregular soft tissue mass with a size of approximately 8.4 cm×6.8 cm×8.3 cm and a uniform density. MRI displayed the cervical mass as isointense on T₁WI, hyperintense on FS-T₂WI and DWI, and hypointense on the corresponding ADC map. Enhanced scans showed marked homogeneous enhancement of the lesion, involving the upper vaginal segment, with multiple lymph nodes seen adjacent to the bilateral iliac vessels. PET/CT showed increased metabolism in cervical masses and left para-iliac lymph nodes. During treatment, PET/CT showed a significant reduction in metabolic activity and size, and the treatment was evaluated as achieving complete remission. Post-treatment, secondary neurolymphomatosis developed. PET/CT showed new hypermetabolic lesions in the right nerve root at the C2/3 level of cervical spine and along the course of the left sciatic nerve in the thigh. A biopsy of the C2/3 cervical spine nerve root lesion confirmed NKTCL infiltration. Conclusions The typical imaging manifestations of primary cervical NKTCL include a large, metabolically active but homogeneous mass with intact cervical mucosa. Imaging examination plays an important role in pre-treatment evaluation, accurate staging, treatment efficacy assessment, recurrence monitoring, and guiding biopsy site selection.

Patients with advanced non-small cell lung cancer (NSCLC) exhibit variable responses to immunotherapy. Therefore, the early and accurate prediction of immunotherapy efficacy is crucial. Currently, artificial intelligence (AI) based on CT imaging are widely utilized for predicting immunotherapy outcomes in advanced NSCLC. This review summarizes the research progress and challenges of AI applications based on CT imaging, specifically in the context of immunotherapy for advanced NSCLC, including the prediction of therapeutic efficacy and prognosis as well as the detection of adverse effects. It also analyzes future research directions and potential development prospects.

Body fat percentage serves as a crucial indicator for measuring an individual’s body fat content. Ultrasound, as a safe and non-invasive examination method, not only enables visual detection of fat layer thickness and effective differentiation between subcutaneous and visceral fat, but also allows assessment of body fat percentage through quantitative measurements of fat thickness at multiple sites. Notably, appropriate selection of measurement sites is particularly beneficial for improving the accuracy of body fat percentage estimation. This review summarizes the potential value, reproducibility, and application ultrasound in measuring subcutaneous and visceral fat for body fat percentage assessment.

Skeletal muscle, as an important component of the skeletal-muscular system, exhibits unique anatomical and structural characteristics. Pathophysiological changes in skeletal muscle are critical to movement, treatment approaches, and prognosis of skeletal muscle diseases. This review provides an overview of MRI-based quantitative parameters used to assess skeletal muscle morphology and histology (such as cross-sectional area, fat content, inflammatory edema status, and muscle fiber structure types), their assessment methods, and clinical applications, as well as the correlation between skeletal muscle health or disease states and MRI-derived quantitative parameters. Additionally, the review highlights recent advances in multimodal MRI for the quantitative evaluation of skeletal muscle structure and function, offering insights into potential clinical applications.